From qa-mobile-pack
Classifies a flaky WDIO/Appium spec as intermittent, deterministic-flake, or locator-broke by analyzing the last 10 BrowserStack runs. Use when the user names a spec and asks "is this flaky", "why is X failing on CI", "should we skip this test", or "triage this flake".
How this skill is triggered — by the user, by Claude, or both
Slash command
/qa-mobile-pack:flake-triageThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Decide whether a spec is genuinely flaky, broken, or hit by a regression. Input `$ARGUMENTS` is the spec name (file path or test title).
Decide whether a spec is genuinely flaky, broken, or hit by a regression. Input $ARGUMENTS is the spec name (file path or test title).
Requires browserstack MCP to pull recent runs — see qa-mobile-pack/mcp/README.md. If unavailable, ask the user to paste the last 10 run summaries (status + failed step + timestamp).
$ARGUMENTS via browserstack MCP, sorted newest-first. For each run capture: status (pass/fail), failed_step, timestamp, app_version or release tag.pass_rate = passes / 10unique_failure_steps = count of distinct failed_step values across the failing runsrecent_pass_rate = passes in runs 1–5 (most recent)older_pass_rate = passes in runs 6–10recent_pass_rate < 0.2 AND older_pass_rate > 0.9 → locator-broke (regression after a release)pass_rate < 0.5 AND unique_failure_steps == 1 → deterministic-flake (same step every fail)pass_rate < 0.5 AND unique_failure_steps >= 2 → intermittent (different steps each fail)stable (do not classify as flake)locator-broke → fix locator; check the latest release diff for the failing screendeterministic-flake → investigate timing or data setup at the failing stepintermittent → file a ticket with the run links; consider retry policy; do not skip yetstable → no action**Spec:** $ARGUMENTS
**Pass rate (last 10):** N/10 (recent 5: N/5, older 5: N/5)
**Unique failure steps:** N
**Classification:** `<intermittent | deterministic-flake | locator-broke | stable>`
**Recommended action:** <action>
**Evidence:**
- <run timestamp> — <status> — <failed_step or "-">
- ... (up to 10)
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub rabusek/qa-mobile-pack